Hands-On Neuroevolution with Python

The evaluate_individ_obj_function function implementation

This function accepts the individual NEAT genome of the objective function candidate and returns the novelty point evaluation results. We implement it as follows:

    n_item = archive.NoveltyItem(generation=generation, genomeId=genome_id)    # run the simulation    multi_net = NEAT.NeuralNetwork()    genome.BuildPhenotype(multi_net)    depth = 2    try:        genome.CalculateDepth()        depth = genome.GetDepth()    except:        pass    obj_net = ANN(multi_net, depth=depth)    # set inputs and get outputs ([a, b])    output = obj_net.activate([0.5])    # store coefficients    n_item.data.append(output[0])    n_item.data.append(output[1])

We start with the creation of a NoveltyItem object to hold the novelty point data for a given genome. ...